HOPE Hospices are still missing HUV windows
Seven months into HOPE implementation, the most common compliance failure is a missed Hospice Update Visit window. Some EMRs shipped templates late, so clinicians double-document.
Healthcare · North America
Your documentation is not the problem. The 6am scramble to backfill a call-out is.
Caregiver turnover is at 79%. The software you bought was designed around the chart, not the caregiver.
75%
caregiver turnover across the home care industry, the lowest reading since 2021.
Source: Activated Insights Benchmarking Report (formerly Home Care Pulse)
In North America
This is what it actually runs on here.
Platforms in this market
- Homecare Homebase
- WellSky
- Axxess
- Netsmart
- HOPE submission
Rules that apply here
- the CMS HOPE assessment
- OASIS-E
- PDGM
- Medicare hospice cap
We read the rule before the call. It is the cheapest way to prove we did the work.
What is happening
The notes are fine. The 6am scramble is the problem.
The real operational pain has moved
Missed visits, late clock-ins, expired certifications, GPS drift on EVV, and a coordinator working the phones at dawn. None of it is a documentation problem.
EVV data that passed in 2025 gets denied in 2026
Claims accepted with marginal electronic visit verification data are now being rejected. The tolerance has gone.
Scheduling and clinical systems do not talk
The coordinator knows who called out. The clinical system knows who was due a visit. Nothing connects them until something is already missed.
However hard, whatever it is
The 6am scramble is one example. Bring the real one.
This page is about filling a gap before the shift. If yours is recruitment, mileage or an assessment window nobody tracks, we work the same way.
-
01 We sit with you
Days where the work happens, not a workshop in a meeting room. We watch the job get done and write down the shortcuts nobody wrote down.
-
02 We read everything
Your data, your rules, your vendors and their documentation, and the published research on your sector. We report what is actually in there.
-
03 We break it to first principles
Not which tool fixes this. What is actually causing it, taken apart until we reach the piece that cannot be divided further.
-
04 Then we build
Weeks, not quarters. By this point we are not guessing what to build, and guessing is the thing that makes projects long.
Where we sit
Your scheduling system stays. We build the morning that runs itself.
4
What you get
- Visits kept Gaps surfaced before they become missed visits
- Clean claims EVV exceptions caught at the point of care
- Compliance HUV and assessment windows tracked, not remembered
3
Built new for you — none of this exists in your stack today
- A carer app that works where there are no bars
- A call-out that fills a gap before 6am
- A small tracker for cars the system cannot see
2
The scheduling layer Reads your rota and visits. Changes nothing without a scheduler saying yes.
Connectors, one agreed meaning per field, and a model reading what no
field holds. Accuracy measured on your own records.
1
- Homecare Homebase
- WellSky
- Axxess
- Netsmart
- HOPE submission
What you already run — unchanged, and still yours
If a carer wrote it, we can capture it. A phone with no signal, a paper visit note, a fax from a surgery. All of it can reach one place.
-
No API -
No documentation -
A terminal from 1994 -
It arrives as paper -
The vendor said no -
It reports nothing
Not a list of limits. Name yours on the call.
And once we can reach it, a model can read it. Most of the value here is in the sources nobody ever structured — the note, the letter, the screen.
Intelligence, plumbed in
A carer's visit note holds the risk. No field does.
We build the reader and the connector, then measure it against notes a clinician has already assessed.
How we make AI survive real data-
Connectors -
A semantic layer -
Evals you can check
What changes
Judge us on this, not on what we built.
Visits kept Gaps surfaced before they become missed visits
Schedule, availability, certification status and visit windows in one place, with the call-out risk visible the evening before, not the morning after.
Clean claims EVV exceptions caught at the point of care
GPS drift, late clock-ins and mismatches flagged while the caregiver is still on site and it can still be fixed.
Compliance HUV and assessment windows tracked, not remembered
With enough warning to act, and an audit trail that shows you did.
Who this is for
The people who feel this first
-
Administrator -
Director of Clinical Services -
Scheduling Manager -
Compliance Officer -
Owner
Straight answers
The questions you would ask on the call
-
Do you replace our EMR?
No. We build the operational layer that sits beside it — scheduling risk, EVV exceptions, compliance windows — and integrate with what you already run.
-
Can you help with HOPE compliance?
Yes, specifically around timeliness. The most common failure is a missed HUV window, and that is a tracking and alerting problem, not a clinical one.
-
How quickly can this be in place?
We read your data first, over a few weeks, so we are both working from your real visit and claim records rather than guesses. A build after that usually takes a few months.
-
Can AI read a carer's visit note reliably?
We measure it against notes a clinician has already assessed, and report accuracy before anyone acts on it. The clinician stays in charge.
Do you know the rules that apply in the United States and Canada?
For home health that means the CMS HOPE assessment, OASIS-E, PDGM and Medicare hospice cap. We read the rule before the call, so the first meeting is about your operation rather than about us catching up.
Whatever home health needs here, we can make it.
What you already run stays where it is. Around it we build software, hardware and the process itself. Here that means a carer app that works where there are no bars.
See everything we build-
Software -
Hardware -
Ways of working -
Whole ventures
Honest about the numbers
The figure above is from Activated Insights Benchmarking Report (formerly Home Care Pulse), for home health.
We have not localised it, because a number nobody can check is worth less than a real one plus this sentence. The pattern travels. The size of it in your market is a question for the call.
Same industry, other markets